A signal processing approach to fair surface design
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Model-based joint motion and structure estimation from stereo images
Computer Vision and Image Understanding
Coding, Analysis, Interpretation, and Recognition of Facial Expressions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Three-Dimensional Human Body Model Acquisition from Multiple Views
International Journal of Computer Vision
Photorealistic Scene Reconstruction by Voxel Coloring
International Journal of Computer Vision
Regularized Bundle-Adjustment to Model Heads from Image Sequences without Calibration Data
International Journal of Computer Vision
Tracking and modeling people in video sequences
Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Robot Vision
The Visual Hull Concept for Silhouette-Based Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Complete Dense Stereovision Using Level Set Methods
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A Passive Full Body Scanner Using Shape from Silhouettes
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
| Hi-index | 0.00 |
We demonstrate a method to automatically extract spatio-temporal descriptions of human faces from synchronized and calibrated multi-view sequences. The head is modeled by a time-varying multi-resolution subdivision surface that is fitted to the observed person using spatio-temporal multi-view stereo information, as well as contour constraints. The stereo data is utilized by computing the normalized correlation between corresponding spatio-temporal image trajectories of surface patches, while the contour information is determined using incremental background subtraction. We globally optimize the shape of the spatio-temporal surface in a coarse-to-fine manner using the multiresolution structure of the subdivision mesh. The method presented incorporates the available image information in a unified framework and automatically reconstructs accurate spatio-temporal representations of complex non-rigidly moving objects.